© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37562
    Prev
    Next
    INDEX
    Explanations

    aviation industry roles and companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨åŃ¦æł¡
    -0.10
    æĪ¿äº§
    -0.10
    æĪ¿åľ°äº§
    -0.09
    çĩ§
    -0.09
    ç¾ŀ
    -0.08
    åīįèĢħ
    -0.08
    å¥ĩçī¹
    -0.08
    è¸ħ
    -0.08
    bsite
    -0.08
    æĹ¥äº§
    -0.08
    POSITIVE LOGITS
    æĹħ客
    0.21
    èĪªç©ºåħ¬åı¸
    0.18
    èĪ±
    0.18
    èĪªçº¿
    0.16
    èĪªçıŃ
    0.16
    å®īæ£Ģ
    0.16
    æ°ijèĪª
    0.16
     airline
    0.16
    æľºåľº
    0.15
    ä¹ĺ客
    0.15
    Activations Density 0.139%

    No Known Activations